import json
import copy
import time
import random
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import matplotlib.pyplot as plt
from matplotlib import pyplot as plt
from torchsummary import summary
from nmfd_gnn import NMFD_GNN
print (torch.cuda.is_available())
device = torch.device("cuda:0")
random_seed = 42
random.seed(random_seed)
torch.manual_seed(random_seed)
torch.cuda.manual_seed(random_seed)
r = random.random
True
#1.1: settings
M = 20 #number of time interval in a window
missing_ratio = 0.50
file_name = "m_" + str(M) + "_missing_" + str(int(missing_ratio*100))
print (file_name)
#1.2: hyperparameters
num_epochs, batch_size, learning_rate = 200, 16, 0.001
beta_flow, beta_occ, beta_phy = 1.0, 1.0, 0.1
batch_size_vt = 16 #batch size for evaluation and test
delta_ratio = 0.1 #the ratio of delta in the standard deviation of flow
hyper = {"n_e": num_epochs, "b_s": batch_size, "b_s_vt": batch_size_vt, "l_r": learning_rate,\
"beta_f": beta_flow, "beta_o": beta_occ, "beta_p": beta_phy, "delta_ratio": delta_ratio}
gnn_dim_1, gnn_dim_2, gnn_dim_3, lstm_dim = 2, 128, 128, 128
p_dim = 10 #column dimension of L1, L2
c_k = 5.5 #meter, the sum of loop width and uniform vehicle length. based on Gero and Daganzo 2008.
theta_ini = [-2.757, 4.996, -2.409, 1.638, 3.569]
hyper_model = {"g_dim_1": gnn_dim_1, "g_dim_2": gnn_dim_2, "g_dim_3": gnn_dim_3, "l_dim": lstm_dim,\
"p_dim": p_dim, "c_k": c_k, "theta_ini": theta_ini}
max_no_decrease = 30
#1.3: set paths
root_path = "/home/umni2/a/umnilab/users/xue120/umni4/2023_mfd_traffic/"
file_path = root_path + "2_prepare_data/" + file_name + "/"
train_path, vali_path, test_path =\
file_path + "train.json", file_path + "vali.json", file_path + "test.json"
sensor_id_path = file_path + "sensor_id_order.json"
sensor_adj_path = file_path + "sensor_adj.json"
mean_std_path = file_path + "mean_std.json"
m_20_missing_50
def visualize_train_loss(total_phy_flow_occ_loss):
plt.figure(figsize=(4,3), dpi=75)
t_p_f_o_l = np.array(total_phy_flow_occ_loss)
e_loss, p_loss, f_loss, o_loss = t_p_f_o_l[:,0], t_p_f_o_l[:,1], t_p_f_o_l[:,2], t_p_f_o_l[:,3]
x = range(len(e_loss))
plt.plot(x, p_loss, linewidth=1, label = "phy loss")
plt.plot(x, f_loss, linewidth=1, label = "flow loss")
plt.plot(x, o_loss, linewidth=1, label = "occ loss")
plt.legend()
plt.title('Loss decline on train')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.savefig(file_name + '/' + 'train_loss.png', bbox_inches = 'tight')
plt.show()
def visualize_flow_loss(vali_f_mae, test_f_mae):
plt.figure(figsize=(4,3), dpi=75)
x = range(len(vali_f_mae))
plt.plot(x, vali_f_mae, linewidth=1, label="Validate")
plt.plot(x, test_f_mae, linewidth=1, label="Test")
plt.legend()
plt.title('MAE of flow on validate/test')
plt.xlabel('Epoch')
plt.ylabel('MAE (veh/h)')
plt.savefig(file_name + '/' + 'flow_mae.png', bbox_inches = 'tight')
plt.show()
def visualize_occ_loss(vali_o_mae, test_o_mae):
plt.figure(figsize=(4,3), dpi=75)
x = range(len(vali_o_mae))
plt.plot(x, vali_o_mae, linewidth=1, label="Validate")
plt.plot(x, test_o_mae, linewidth=1, label="Test")
plt.legend()
plt.title('MAE of occupancy on validate/test')
plt.xlabel('Epoch')
plt.ylabel('MAE')
plt.savefig(file_name + '/' + 'occ_mae.png',bbox_inches = 'tight')
plt.show()
def MAELoss(yhat, y):
return float(torch.mean(torch.div(torch.abs(yhat-y), 1)))
def RMSELoss(yhat, y):
return float(torch.sqrt(torch.mean((yhat-y)**2)))
def vali_test(model, f, f_mask, o, o_mask, f_o_mean_std, b_s_vt):
flow_std, occ_std, n = f_o_mean_std[1], f_o_mean_std[3], len(f)
f_mae_list, f_rmse_list, o_mae_list, o_rmse_list, num_list = list(), list(), list(), list(), list()
for i in range(0, n, b_s_vt):
s, e = i, np.min([i+b_s_vt, n])
num_list.append(e-s)
bf, bo, bf_mask, bo_mask = f[s: e], o[s: e], f_mask[s: e], o_mask[s: e]
bf_hat, bo_hat, bq_hat, bq_theta = model.run(bf_mask, bo_mask)
bf_hat, bo_hat = bf_hat.cpu(), bo_hat.cpu()
bf_mae, bf_rmse = MAELoss(bf_hat, bf)*flow_std, RMSELoss(bf_hat, bf)*flow_std
bo_mae, bo_rmse = MAELoss(bo_hat, bo)*occ_std, RMSELoss(bo_hat, bo)*occ_std
f_mae_list.append(bf_mae)
f_rmse_list.append(bf_rmse)
o_mae_list.append(bo_mae)
o_rmse_list.append(bo_rmse)
f_mae, o_mae = np.dot(f_mae_list, num_list)/n, np.dot(o_mae_list, num_list)/n
f_rmse = np.sqrt(np.dot(np.multiply(f_rmse_list, f_rmse_list), num_list)/n)
o_rmse = np.sqrt(np.dot(np.multiply(o_rmse_list, o_rmse_list), num_list)/n)
return f_mae, f_rmse, o_mae, o_rmse
def evaluate(model, vt_f, vt_o, vt_f_m, vt_o_m, f_o_mean_std, b_s_vt): #vt: vali_test
vt_f_mae, vt_f_rmse, vt_o_mae, vt_o_rmse =\
vali_test(model, vt_f, vt_f_m, vt_o, vt_o_m, f_o_mean_std, b_s_vt)
return vt_f_mae, vt_f_rmse, vt_o_mae, vt_o_rmse
import torch
#4.1: one training epoch
def train_epoch(model, opt, criterion, train_f_x, train_f_y, train_o_x, train_o_y, hyper, flow_std_squ, delta):
#f: flow; o: occupancy
model.train()
losses, p_losses, f_losses, o_losses = list(), list(), list(), list()
beta_f, beta_o, beta_p, b_s = hyper["beta_f"], hyper["beta_o"], hyper["beta_p"], hyper["b_s"]
n = len(train_f_x)
print ("# batch: ", int(n/b_s))
for i in range(0, n-b_s, b_s):
time1 = time.time()
x_f_batch, y_f_batch = train_f_x[i: i+b_s], train_f_y[i: i+b_s]
x_o_batch, y_o_batch = train_o_x[i: i+b_s], train_o_y[i: i+b_s]
opt.zero_grad()
y_f_hat, y_o_hat, q_hat, q_theta = model.run(x_f_batch, x_o_batch)
#p_loss = criterion(q_hat, q_theta).cpu() #physical loss
#p_loss = p_loss/flow_std_squ
#hinge loss
q_gap = q_hat - q_theta
delta_gap = torch.ones(q_gap.shape, device=device)*delta
zero_gap = torch.zeros(q_gap.shape, device=device) #(n, m)
hl_loss = torch.max(q_gap-delta_gap, zero_gap) + torch.max(-delta_gap-q_gap, zero_gap)
hl_loss = hl_loss/flow_std_squ
p_loss = criterion(hl_loss, zero_gap).cpu() #(n, m)
f_loss = criterion(y_f_hat.cpu(), y_f_batch) #data loss of flow
o_loss = criterion(y_o_hat.cpu(), y_o_batch) #data loss of occupancy
loss = beta_f*f_loss + beta_o*o_loss + beta_p*p_loss
loss.backward()
opt.step()
losses.append(loss.data.numpy())
p_losses.append(p_loss.data.numpy())
f_losses.append(f_loss.data.numpy())
o_losses.append(o_loss.data.numpy())
if i % (64*b_s) == 0:
print ("i_batch: ", i/b_s)
print ("the loss for this batch: ", loss.data.numpy())
print ("flow loss", f_loss.data.numpy())
print ("occ loss", o_loss.data.numpy())
time2 = time.time()
print ("time for this batch", time2-time1)
print ("----------------------------------")
n_loss = float(len(losses)+0.000001)
aver_loss = sum(losses)/n_loss
aver_p_loss = sum(p_losses)/n_loss
aver_f_loss = sum(f_losses)/n_loss
aver_o_loss = sum(o_losses)/n_loss
return aver_loss, model, aver_p_loss, aver_f_loss, aver_o_loss
#4.2: all train epochs
def train_process(model, criterion, train, vali, test, hyper, f_o_mean_std):
total_phy_flow_occ_loss = list()
n_mse_flow_occ = 0 #mse(flow) + mse(occ) for validation sets.
f_std = f_o_mean_std[1]
vali_f, vali_o = vali["flow"], vali["occupancy"]
vali_f_m, vali_o_m = vali["flow_mask"].to(device), vali["occupancy_mask"].to(device)
test_f, test_o = test["flow"], test["occupancy"]
test_f_m, test_o_m = test["flow_mask"].to(device), test["occupancy_mask"].to(device)
l_r, n_e = hyper["l_r"], hyper["n_e"]
opt = optim.Adam(model.parameters(), l_r, betas = (0.9,0.999), weight_decay=0.0001)
opt_scheduler = torch.optim.lr_scheduler.MultiStepLR(opt, milestones=[150])
print ("# epochs ", n_e)
r_vali_f_mae, r_vali_o_mae, r_test_f_mae, r_test_o_mae = list(), list(), list(), list()
r_vali_f_rmse, r_vali_o_rmse, r_test_f_rmse, r_test_o_rmse = list(), list(), list(), list()
flow_std_squ = np.power(f_std, 2)
no_decrease = 0
for i in range(n_e):
print ("----------------an epoch starts-------------------")
#time1_s = time.time()
time_s = time.time()
print ("i_epoch: ", i)
n_train = len(train["flow"])
number_list = copy.copy(list(range(n_train)))
random.shuffle(number_list, random = r)
shuffle_idx = torch.tensor(number_list)
train_x_f, train_y_f = train["flow_mask"][shuffle_idx], train["flow"][shuffle_idx]
train_x_o, train_y_o = train["occupancy_mask"][shuffle_idx], train["occupancy"][shuffle_idx]
delta = hyper["delta_ratio"] * f_std
aver_loss, model, aver_p_loss, aver_f_loss, aver_o_loss =\
train_epoch(model, opt, criterion, train_x_f.to(device), train_y_f,\
train_x_o.to(device), train_y_o, hyper, flow_std_squ, delta)
opt_scheduler.step()
total_phy_flow_occ_loss.append([aver_loss, aver_p_loss, aver_f_loss, aver_o_loss])
print ("train loss for this epoch: ", round(aver_loss, 6))
#evaluate
b_s_vt = hyper["b_s_vt"]
vali_f_mae, vali_f_rmse, vali_o_mae, vali_o_rmse =\
evaluate(model, vali_f, vali_o, vali_f_m, vali_o_m, f_o_mean_std, b_s_vt)
test_f_mae, test_f_rmse, test_o_mae, test_o_rmse =\
evaluate(model, test_f, test_o, test_f_m, test_o_m, f_o_mean_std, b_s_vt)
r_vali_f_mae.append(vali_f_mae)
r_test_f_mae.append(test_f_mae)
r_vali_o_mae.append(vali_o_mae)
r_test_o_mae.append(test_o_mae)
r_vali_f_rmse.append(vali_f_rmse)
r_test_f_rmse.append(test_f_rmse)
r_vali_o_rmse.append(vali_o_rmse)
r_test_o_rmse.append(test_o_rmse)
visualize_train_loss(total_phy_flow_occ_loss)
visualize_flow_loss(r_vali_f_mae, r_test_f_mae)
visualize_occ_loss(r_vali_o_mae, r_test_o_mae)
time_e = time.time()
print ("time for this epoch", time_e - time_s)
performance = {"train": total_phy_flow_occ_loss,\
"vali": [r_vali_f_mae, r_vali_f_rmse, r_vali_o_mae, r_vali_o_rmse],\
"test": [r_test_f_mae, r_test_f_rmse, r_test_o_mae, r_test_o_rmse]}
subfile = open(file_name + '/' + 'performance'+'.json','w')
json.dump(performance, subfile)
subfile.close()
#early stop
flow_std, occ_std = f_o_mean_std[1], f_o_mean_std[3]
norm_f_rmse, norm_o_rmse = vali_f_rmse/flow_std, vali_o_rmse/occ_std
norm_sum_mse = norm_f_rmse*norm_f_rmse + norm_o_rmse*norm_o_rmse
if n_mse_flow_occ > 0:
min_until_now = min([min_until_now, norm_sum_mse])
else:
min_until_now = 1000000.0
if norm_sum_mse > min_until_now:
no_decrease = no_decrease+1
else:
no_decrease = 0
if no_decrease == max_no_decrease:
print ("Early stop at the " + str(i+1) + "-th epoch")
return total_phy_flow_occ_loss, model
n_mse_flow_occ = n_mse_flow_occ + 1
print ("No_decrease: ", no_decrease)
return total_phy_flow_occ_loss, model
def tensorize(train_vali_test):
result = dict()
result["flow"] = torch.tensor(train_vali_test["flow"])
result["flow_mask"] = torch.tensor(train_vali_test["flow_mask"])
result["occupancy"] = torch.tensor(train_vali_test["occupancy"])
result["occupancy_mask"] = torch.tensor(train_vali_test["occupancy_mask"])
return result
def normalize_flow_occ(tvt, f_o_mean_std): #tvt: train, vali, test
#flow
f_mean, f_std = f_o_mean_std[0], f_o_mean_std[1]
f_mask, f = tvt["flow_mask"], tvt["flow"]
tvt["flow_mask"] = ((np.array(f_mask)-f_mean)/f_std).tolist()
tvt["flow"] = ((np.array(f)-f_mean)/f_std).tolist()
#occ
o_mean, o_std = f_o_mean_std[2], f_o_mean_std[3]
o_mask, o = tvt["occupancy_mask"], tvt["occupancy"]
tvt["occupancy_mask"] = ((np.array(o_mask)-o_mean)/o_std).tolist()
tvt["occupancy"] = ((np.array(o)-o_mean)/o_std).tolist()
return tvt
def transform_distance(d_matrix):
sigma, n_row, n_col = np.std(d_matrix), len(d_matrix), len(d_matrix[0])
sigma_square = sigma*sigma
for i in range(n_row):
for j in range(n_col):
d_i_j = d_matrix[i][j]
d_matrix[i][j] = np.exp(0.0-10000.0*d_i_j*d_i_j/sigma_square)
return d_matrix
def load_data(train_path, vali_path, test_path, sensor_adj_path, mean_std_path, sensor_id_path):
mean_std = json.load(open(mean_std_path))
f_mean, f_std, o_mean, o_std =\
mean_std["f_mean"], mean_std["f_std"], mean_std["o_mean"], mean_std["o_std"]
f_o_mean_std = [f_mean, f_std, o_mean, o_std]
train = json.load(open(train_path))
vali = json.load(open(vali_path))
test = json.load(open(test_path))
adj = json.load(open(sensor_adj_path))["adj"]
n_sensor = len(train["flow"][0])
train = tensorize(normalize_flow_occ(train, f_o_mean_std))
vali = tensorize(normalize_flow_occ(vali, f_o_mean_std))
test = tensorize(normalize_flow_occ(test, f_o_mean_std))
adj = torch.tensor(transform_distance(adj), device=device).float()
df_sensor_id = json.load(open(sensor_id_path))
sensor_length = [0.0 for i in range(n_sensor)]
for sensor in df_sensor_id:
sensor_length[df_sensor_id[sensor][0]] = df_sensor_id[sensor][3]
return train, vali, test, adj, n_sensor, f_o_mean_std, sensor_length
#6.1 load the data
time1 = time.time()
train, vali, test, adj, n_sensor, f_o_mean_std, sensor_length =\
load_data(train_path, vali_path, test_path, sensor_adj_path, mean_std_path, sensor_id_path)
time2 = time.time()
print (time2-time1)
18.573214054107666
print (len(train["flow"]))
print (len(vali["flow"]))
print (len(test["flow"]))
print (f_o_mean_std)
1997 653 653 [241.21586152814126, 220.92336003653475, 0.13805152810287494, 0.1920120065038222]
model = NMFD_GNN(n_sensor, M, hyper_model, f_o_mean_std, sensor_length, adj).to(device)
cri = nn.MSELoss()
#6.2: train the model
total_phy_flow_occ_loss, trained_model = train_process(model, cri, train, vali, test, hyper, f_o_mean_std)
# epochs 200 ----------------an epoch starts------------------- i_epoch: 0 # batch: 124 i_batch: 0.0 the loss for this batch: 1.71809 flow loss 0.89621675 occ loss 0.82187146 time for this batch 0.6436805725097656 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.45944092 flow loss 0.16827554 occ loss 0.29116258 time for this batch 0.36271119117736816 ---------------------------------- train loss for this epoch: 0.591072
time for this epoch 56.651963233947754 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 1 # batch: 124 i_batch: 0.0 the loss for this batch: 0.42612982 flow loss 0.14691354 occ loss 0.279213 time for this batch 0.3153653144836426 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.47933322 flow loss 0.15097466 occ loss 0.32835498 time for this batch 0.38279104232788086 ---------------------------------- train loss for this epoch: 0.375155
time for this epoch 57.072731018066406 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 2 # batch: 124 i_batch: 0.0 the loss for this batch: 0.27988362 flow loss 0.09501598 occ loss 0.18486524 time for this batch 0.37389445304870605 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.32103604 flow loss 0.10087322 occ loss 0.22015983 time for this batch 0.4050748348236084 ---------------------------------- train loss for this epoch: 0.336523
time for this epoch 62.66493630409241 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 3 # batch: 124 i_batch: 0.0 the loss for this batch: 0.33583727 flow loss 0.10371247 occ loss 0.2321219 time for this batch 0.33260416984558105 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.34449634 flow loss 0.09586112 occ loss 0.24863279 time for this batch 0.43418192863464355 ---------------------------------- train loss for this epoch: 0.316722
time for this epoch 63.27169585227966 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 4 # batch: 124 i_batch: 0.0 the loss for this batch: 0.36231226 flow loss 0.10087846 occ loss 0.2614305 time for this batch 0.3613440990447998 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.29859093 flow loss 0.085553914 occ loss 0.21303426 time for this batch 0.43465113639831543 ---------------------------------- train loss for this epoch: 0.305296
time for this epoch 69.3442931175232 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 5 # batch: 124 i_batch: 0.0 the loss for this batch: 0.3121631 flow loss 0.091825366 occ loss 0.22033463 time for this batch 0.38411378860473633 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19562195 flow loss 0.06497544 occ loss 0.1306447 time for this batch 0.42182183265686035 ---------------------------------- train loss for this epoch: 0.297636
time for this epoch 66.75419640541077 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 6 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25688508 flow loss 0.08622245 occ loss 0.17065994 time for this batch 0.365706205368042 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2336505 flow loss 0.074063204 occ loss 0.159585 time for this batch 0.4120488166809082 ---------------------------------- train loss for this epoch: 0.290509
time for this epoch 63.651856899261475 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 7 # batch: 124 i_batch: 0.0 the loss for this batch: 0.22877006 flow loss 0.066490635 occ loss 0.16227767 time for this batch 0.33281397819519043 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.29710495 flow loss 0.08541275 occ loss 0.21168904 time for this batch 0.42058801651000977 ---------------------------------- train loss for this epoch: 0.285314
time for this epoch 64.46010613441467 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 8 # batch: 124 i_batch: 0.0 the loss for this batch: 0.33263186 flow loss 0.09582901 occ loss 0.23679972 time for this batch 0.3671262264251709 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23194857 flow loss 0.06785423 occ loss 0.164092 time for this batch 0.42928004264831543 ---------------------------------- train loss for this epoch: 0.2799
time for this epoch 63.935362339019775 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 9 # batch: 124 i_batch: 0.0 the loss for this batch: 0.3675995 flow loss 0.09699231 occ loss 0.2706036 time for this batch 0.3756434917449951 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.33954108 flow loss 0.09046857 occ loss 0.24906915 time for this batch 0.4548826217651367 ---------------------------------- train loss for this epoch: 0.275519
time for this epoch 64.61618542671204 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 10 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21049699 flow loss 0.0649654 occ loss 0.14552923 time for this batch 0.3508491516113281 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22128566 flow loss 0.06449693 occ loss 0.15678622 time for this batch 0.427565336227417 ---------------------------------- train loss for this epoch: 0.27193
time for this epoch 64.63073778152466 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 11 # batch: 124 i_batch: 0.0 the loss for this batch: 0.27655515 flow loss 0.07986489 occ loss 0.196687 time for this batch 0.38117480278015137 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.18558463 flow loss 0.0587819 occ loss 0.12680069 time for this batch 0.416989803314209 ---------------------------------- train loss for this epoch: 0.26844
time for this epoch 65.28579902648926 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 12 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25190794 flow loss 0.071572185 occ loss 0.18033287 time for this batch 0.3795349597930908 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.3218456 flow loss 0.08497126 occ loss 0.23687083 time for this batch 0.47234296798706055 ---------------------------------- train loss for this epoch: 0.264991
time for this epoch 64.894700050354 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 13 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23337115 flow loss 0.07406184 occ loss 0.15930673 time for this batch 0.39777088165283203 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.30133158 flow loss 0.086550094 occ loss 0.21477836 time for this batch 0.40256643295288086 ---------------------------------- train loss for this epoch: 0.263387
time for this epoch 66.8178186416626 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 14 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2866698 flow loss 0.08193627 occ loss 0.20473032 time for this batch 0.39766716957092285 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.32276452 flow loss 0.086743414 occ loss 0.23601785 time for this batch 0.44763636589050293 ---------------------------------- train loss for this epoch: 0.259706
time for this epoch 66.70117354393005 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 15 # batch: 124 i_batch: 0.0 the loss for this batch: 0.28736165 flow loss 0.07667008 occ loss 0.21068843 time for this batch 0.3534109592437744 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.26993945 flow loss 0.076713435 occ loss 0.19322322 time for this batch 0.37622642517089844 ---------------------------------- train loss for this epoch: 0.258619
time for this epoch 59.13344979286194 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 16 # batch: 124 i_batch: 0.0 the loss for this batch: 0.26580352 flow loss 0.074383475 occ loss 0.19141677 time for this batch 0.3821907043457031 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22406171 flow loss 0.07126738 occ loss 0.15279196 time for this batch 0.3783698081970215 ---------------------------------- train loss for this epoch: 0.257553
time for this epoch 64.65511655807495 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 17 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20515211 flow loss 0.063593164 occ loss 0.14155681 time for this batch 0.3908071517944336 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22633478 flow loss 0.061244547 occ loss 0.16508782 time for this batch 0.43149352073669434 ---------------------------------- train loss for this epoch: 0.254198
time for this epoch 63.884684324264526 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 18 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25871336 flow loss 0.071762316 occ loss 0.18694781 time for this batch 0.35426783561706543 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22252224 flow loss 0.06625383 occ loss 0.15626566 time for this batch 0.4129810333251953 ---------------------------------- train loss for this epoch: 0.253095
time for this epoch 64.77478098869324 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 19 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20951225 flow loss 0.059287425 occ loss 0.15022269 time for this batch 0.34084296226501465 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2416055 flow loss 0.06398504 occ loss 0.17761824 time for this batch 0.37480807304382324 ---------------------------------- train loss for this epoch: 0.252203
time for this epoch 66.32376456260681 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 20 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2588602 flow loss 0.06510005 occ loss 0.19375746 time for this batch 0.36916685104370117 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2182679 flow loss 0.06336883 occ loss 0.15489665 time for this batch 0.428253173828125 ---------------------------------- train loss for this epoch: 0.250537
time for this epoch 64.74082684516907 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 21 # batch: 124 i_batch: 0.0 the loss for this batch: 0.16020529 flow loss 0.052411098 occ loss 0.10779229 time for this batch 0.3497593402862549 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.28386623 flow loss 0.078991756 occ loss 0.20487136 time for this batch 0.4232602119445801 ---------------------------------- train loss for this epoch: 0.250272
time for this epoch 63.380616664886475 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 22 # batch: 124 i_batch: 0.0 the loss for this batch: 0.34749427 flow loss 0.088564806 occ loss 0.2589261 time for this batch 0.35246753692626953 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.29780117 flow loss 0.08107718 occ loss 0.21672037 time for this batch 0.4185497760772705 ---------------------------------- train loss for this epoch: 0.247475
time for this epoch 65.54675459861755 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 23 # batch: 124 i_batch: 0.0 the loss for this batch: 0.26502445 flow loss 0.071315244 occ loss 0.19370604 time for this batch 0.35578322410583496 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20670769 flow loss 0.059279762 occ loss 0.14742517 time for this batch 0.415050745010376 ---------------------------------- train loss for this epoch: 0.249433
time for this epoch 63.95142149925232 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 24 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24722666 flow loss 0.07072515 occ loss 0.17649859 time for this batch 0.36197757720947266 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19174835 flow loss 0.057436552 occ loss 0.13430956 time for this batch 0.39067864418029785 ---------------------------------- train loss for this epoch: 0.243871
time for this epoch 64.17225384712219 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 25 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23850851 flow loss 0.06426033 occ loss 0.17424552 time for this batch 0.3729565143585205 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.26258808 flow loss 0.06753069 occ loss 0.19505489 time for this batch 0.3800477981567383 ---------------------------------- train loss for this epoch: 0.242987
time for this epoch 64.89483594894409 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 26 # batch: 124 i_batch: 0.0 the loss for this batch: 0.35642883 flow loss 0.08662004 occ loss 0.26980442 time for this batch 0.39039015769958496 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.29992503 flow loss 0.083970256 occ loss 0.21595122 time for this batch 0.41928791999816895 ---------------------------------- train loss for this epoch: 0.242851
time for this epoch 64.83832621574402 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 27 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20987357 flow loss 0.0572135 occ loss 0.15265809 time for this batch 0.42040109634399414 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2714127 flow loss 0.07277812 occ loss 0.1986315 time for this batch 0.4040837287902832 ---------------------------------- train loss for this epoch: 0.242959
time for this epoch 69.0268759727478 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 28 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23782761 flow loss 0.06516386 occ loss 0.1726609 time for this batch 0.3793373107910156 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24476127 flow loss 0.0650164 occ loss 0.17974208 time for this batch 0.4823179244995117 ---------------------------------- train loss for this epoch: 0.24135
time for this epoch 67.80516147613525 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 29 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2292964 flow loss 0.06340987 occ loss 0.16588354 time for this batch 0.3610537052154541 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.3239938 flow loss 0.08405252 occ loss 0.23993738 time for this batch 0.4557466506958008 ---------------------------------- train loss for this epoch: 0.241327
time for this epoch 70.21272778511047 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 30 # batch: 124 i_batch: 0.0 the loss for this batch: 0.31835616 flow loss 0.08523356 occ loss 0.23311856 time for this batch 0.39962005615234375 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.27211916 flow loss 0.07518705 occ loss 0.19692853 time for this batch 0.3466031551361084 ---------------------------------- train loss for this epoch: 0.241077
time for this epoch 66.04447984695435 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 31 # batch: 124 i_batch: 0.0 the loss for this batch: 0.3011439 flow loss 0.07968054 occ loss 0.22145936 time for this batch 0.3955063819885254 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2581313 flow loss 0.07037145 occ loss 0.18775672 time for this batch 0.4336435794830322 ---------------------------------- train loss for this epoch: 0.239229
time for this epoch 64.47346448898315 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 32 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19770116 flow loss 0.05062636 occ loss 0.14707288 time for this batch 0.35108494758605957 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21681209 flow loss 0.060616545 occ loss 0.15619282 time for this batch 0.3938777446746826 ---------------------------------- train loss for this epoch: 0.236086
time for this epoch 63.49710941314697 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 33 # batch: 124 i_batch: 0.0 the loss for this batch: 0.242918 flow loss 0.066263765 occ loss 0.1766513 time for this batch 0.3493030071258545 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21546519 flow loss 0.059429023 occ loss 0.15603371 time for this batch 0.4096810817718506 ---------------------------------- train loss for this epoch: 0.235828
time for this epoch 63.68162393569946 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 34 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2596576 flow loss 0.069988005 occ loss 0.18966678 time for this batch 0.3701791763305664 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25243866 flow loss 0.068119094 occ loss 0.18431666 time for this batch 0.4254179000854492 ---------------------------------- train loss for this epoch: 0.23697
time for this epoch 64.32600164413452 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 35 # batch: 124 i_batch: 0.0 the loss for this batch: 0.27059633 flow loss 0.073205486 occ loss 0.19738734 time for this batch 0.3563973903656006 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21973556 flow loss 0.0642729 occ loss 0.15545996 time for this batch 0.42598986625671387 ---------------------------------- train loss for this epoch: 0.234385
time for this epoch 63.46278715133667 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 36 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23800361 flow loss 0.06321205 occ loss 0.17478888 time for this batch 0.33332347869873047 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24006633 flow loss 0.07001167 occ loss 0.17005186 time for this batch 0.3976266384124756 ---------------------------------- train loss for this epoch: 0.23355
time for this epoch 64.43727254867554 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 37 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18172872 flow loss 0.052797403 occ loss 0.12892908 time for this batch 0.3683168888092041 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20891164 flow loss 0.0575725 occ loss 0.15133661 time for this batch 0.3508412837982178 ---------------------------------- train loss for this epoch: 0.234249
time for this epoch 65.18748092651367 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 38 # batch: 124 i_batch: 0.0 the loss for this batch: 0.32985097 flow loss 0.08433094 occ loss 0.24551633 time for this batch 0.401993989944458 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2883162 flow loss 0.07811826 occ loss 0.21019426 time for this batch 0.42810606956481934 ---------------------------------- train loss for this epoch: 0.232391
time for this epoch 65.4538459777832 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 39 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24272805 flow loss 0.06513733 occ loss 0.17758751 time for this batch 0.3680739402770996 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.32060355 flow loss 0.08057562 occ loss 0.24002427 time for this batch 0.4500746726989746 ---------------------------------- train loss for this epoch: 0.233282
time for this epoch 63.88539910316467 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 40 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25872058 flow loss 0.07232709 occ loss 0.18639052 time for this batch 0.34786105155944824 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17480801 flow loss 0.05175481 occ loss 0.123050906 time for this batch 0.44106411933898926 ---------------------------------- train loss for this epoch: 0.2327
time for this epoch 64.7789409160614 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 41 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21076715 flow loss 0.058388114 occ loss 0.15237683 time for this batch 0.341672420501709 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21167353 flow loss 0.06141482 occ loss 0.15025611 time for this batch 0.43860721588134766 ---------------------------------- train loss for this epoch: 0.230426
time for this epoch 64.25742530822754 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 42 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18990739 flow loss 0.053275097 occ loss 0.13663013 time for this batch 0.41446971893310547 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.26890188 flow loss 0.07273486 occ loss 0.19616394 time for this batch 0.5202672481536865 ---------------------------------- train loss for this epoch: 0.23082
time for this epoch 64.41082382202148 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 43 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25010574 flow loss 0.07520906 occ loss 0.17489398 time for this batch 0.3725762367248535 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.32665837 flow loss 0.08441556 occ loss 0.24223883 time for this batch 0.42867231369018555 ---------------------------------- train loss for this epoch: 0.231004
time for this epoch 67.20598864555359 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 44 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19635737 flow loss 0.06067921 occ loss 0.13567542 time for this batch 0.39113616943359375 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25014028 flow loss 0.066013284 occ loss 0.18412378 time for this batch 0.4123568534851074 ---------------------------------- train loss for this epoch: 0.230145
time for this epoch 64.10445022583008 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 45 # batch: 124 i_batch: 0.0 the loss for this batch: 0.31754395 flow loss 0.07883849 occ loss 0.2387017 time for this batch 0.34261441230773926 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.18968451 flow loss 0.05161058 occ loss 0.13807185 time for this batch 0.41130948066711426 ---------------------------------- train loss for this epoch: 0.229636
time for this epoch 64.36573147773743 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 46 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21825178 flow loss 0.061199468 occ loss 0.15704957 time for this batch 0.3446340560913086 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22188511 flow loss 0.060716923 occ loss 0.16116546 time for this batch 0.4124178886413574 ---------------------------------- train loss for this epoch: 0.229313
time for this epoch 62.814361810684204 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 47 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19383326 flow loss 0.055853937 occ loss 0.13797687 time for this batch 0.35428786277770996 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20427732 flow loss 0.062209178 occ loss 0.14206594 time for this batch 0.43318748474121094 ---------------------------------- train loss for this epoch: 0.232253
time for this epoch 64.99364304542542 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 48 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20179757 flow loss 0.057495087 occ loss 0.14430018 time for this batch 0.36868858337402344 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2616205 flow loss 0.06864457 occ loss 0.19297336 time for this batch 0.4434854984283447 ---------------------------------- train loss for this epoch: 0.228834
time for this epoch 61.86514902114868 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 49 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24282022 flow loss 0.0672114 occ loss 0.17560552 time for this batch 0.33675146102905273 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24381872 flow loss 0.06844699 occ loss 0.17536825 time for this batch 0.3940401077270508 ---------------------------------- train loss for this epoch: 0.227468
time for this epoch 63.64828038215637 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 50 # batch: 124 i_batch: 0.0 the loss for this batch: 0.29709285 flow loss 0.071635105 occ loss 0.22545421 time for this batch 0.3619868755340576 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.30997446 flow loss 0.07217752 occ loss 0.23779386 time for this batch 0.4433279037475586 ---------------------------------- train loss for this epoch: 0.228276
time for this epoch 64.01695442199707 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 51 # batch: 124 i_batch: 0.0 the loss for this batch: 0.22545177 flow loss 0.06674571 occ loss 0.15870291 time for this batch 0.359757661819458 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2810832 flow loss 0.07387729 occ loss 0.20720235 time for this batch 0.44173598289489746 ---------------------------------- train loss for this epoch: 0.226622
time for this epoch 66.42050504684448 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 52 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20039037 flow loss 0.05416176 occ loss 0.14622593 time for this batch 0.3487720489501953 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.14702086 flow loss 0.049383666 occ loss 0.09763548 time for this batch 0.42950868606567383 ---------------------------------- train loss for this epoch: 0.226958
time for this epoch 64.27875185012817 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 53 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23997346 flow loss 0.062373467 occ loss 0.17759702 time for this batch 0.4104342460632324 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23941071 flow loss 0.063444346 occ loss 0.17596349 time for this batch 0.37542152404785156 ---------------------------------- train loss for this epoch: 0.226078
time for this epoch 63.940758228302 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 54 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23415753 flow loss 0.06279874 occ loss 0.17135552 time for this batch 0.36652207374572754 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.16437222 flow loss 0.051419232 occ loss 0.11295083 time for this batch 0.42168307304382324 ---------------------------------- train loss for this epoch: 0.227415
time for this epoch 65.6561291217804 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 55 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23985972 flow loss 0.060905688 occ loss 0.17895134 time for this batch 0.41462278366088867 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21243352 flow loss 0.05765971 occ loss 0.15477121 time for this batch 0.4129960536956787 ---------------------------------- train loss for this epoch: 0.225737
time for this epoch 66.59704542160034 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 56 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24480645 flow loss 0.062685244 occ loss 0.18211806 time for this batch 0.35903358459472656 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.29190022 flow loss 0.074007355 occ loss 0.21788949 time for this batch 0.39679622650146484 ---------------------------------- train loss for this epoch: 0.225858
time for this epoch 64.35539102554321 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 57 # batch: 124 i_batch: 0.0 the loss for this batch: 0.22218587 flow loss 0.060616266 occ loss 0.1615668 time for this batch 0.3524298667907715 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17593156 flow loss 0.05190058 occ loss 0.12402888 time for this batch 0.39269089698791504 ---------------------------------- train loss for this epoch: 0.225345
time for this epoch 62.3412561416626 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 58 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18208057 flow loss 0.054353576 occ loss 0.12772483 time for this batch 0.3690650463104248 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24817094 flow loss 0.06573516 occ loss 0.18243329 time for this batch 0.40694308280944824 ---------------------------------- train loss for this epoch: 0.224471
time for this epoch 64.46356177330017 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 59 # batch: 124 i_batch: 0.0 the loss for this batch: 0.1727084 flow loss 0.0522848 occ loss 0.12042116 time for this batch 0.34128499031066895 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22629435 flow loss 0.05933137 occ loss 0.16696006 time for this batch 0.41646385192871094 ---------------------------------- train loss for this epoch: 0.225295
time for this epoch 64.17399549484253 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 60 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25879002 flow loss 0.06858427 occ loss 0.19020276 time for this batch 0.3576481342315674 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22250508 flow loss 0.059068415 occ loss 0.16343378 time for this batch 0.4192972183227539 ---------------------------------- train loss for this epoch: 0.224667
time for this epoch 64.34464025497437 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 61 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20915931 flow loss 0.060053244 occ loss 0.14910342 time for this batch 0.3416423797607422 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.16592883 flow loss 0.04606413 occ loss 0.11986268 time for this batch 0.45147109031677246 ---------------------------------- train loss for this epoch: 0.226334
time for this epoch 65.75423264503479 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 62 # batch: 124 i_batch: 0.0 the loss for this batch: 0.15180781 flow loss 0.048779298 occ loss 0.10302654 time for this batch 0.3544321060180664 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25771496 flow loss 0.06799482 occ loss 0.18971731 time for this batch 0.3768117427825928 ---------------------------------- train loss for this epoch: 0.223232
time for this epoch 63.73007249832153 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 63 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2380642 flow loss 0.06795489 occ loss 0.17010573 time for this batch 0.353867769241333 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20305862 flow loss 0.054985866 occ loss 0.14807028 time for this batch 0.3829801082611084 ---------------------------------- train loss for this epoch: 0.223967
time for this epoch 65.26282024383545 No_decrease: 7 ----------------an epoch starts------------------- i_epoch: 64 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2234475 flow loss 0.061889693 occ loss 0.16155514 time for this batch 0.3973197937011719 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22400141 flow loss 0.057268668 occ loss 0.16673 time for this batch 0.3771805763244629 ---------------------------------- train loss for this epoch: 0.224949
time for this epoch 60.672324419021606 No_decrease: 8 ----------------an epoch starts------------------- i_epoch: 65 # batch: 124 i_batch: 0.0 the loss for this batch: 0.1987433 flow loss 0.05787281 occ loss 0.14086765 time for this batch 0.37136387825012207 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.090994075 flow loss 0.030529562 occ loss 0.060463462 time for this batch 0.3760867118835449 ---------------------------------- train loss for this epoch: 0.222711
time for this epoch 63.15388751029968 No_decrease: 9 ----------------an epoch starts------------------- i_epoch: 66 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23881267 flow loss 0.06711008 occ loss 0.17169966 time for this batch 0.35690736770629883 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24557735 flow loss 0.06349233 occ loss 0.18208203 time for this batch 0.4288156032562256 ---------------------------------- train loss for this epoch: 0.22258
time for this epoch 63.93661284446716 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 67 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2329667 flow loss 0.06546122 occ loss 0.16750237 time for this batch 0.37597060203552246 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21284042 flow loss 0.057637293 occ loss 0.15520035 time for this batch 0.4234621524810791 ---------------------------------- train loss for this epoch: 0.221841
time for this epoch 63.925387382507324 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 68 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17003407 flow loss 0.051116023 occ loss 0.11891582 time for this batch 0.3694424629211426 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17708851 flow loss 0.04874417 occ loss 0.12834242 time for this batch 0.442047119140625 ---------------------------------- train loss for this epoch: 0.221931
time for this epoch 65.47655534744263 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 69 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2429203 flow loss 0.063971564 occ loss 0.17894572 time for this batch 0.36678290367126465 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24554671 flow loss 0.07185016 occ loss 0.17369358 time for this batch 0.47247767448425293 ---------------------------------- train loss for this epoch: 0.222488
time for this epoch 70.65302109718323 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 70 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21326977 flow loss 0.052657288 occ loss 0.16060972 time for this batch 0.3832573890686035 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1948736 flow loss 0.053702876 occ loss 0.14116804 time for this batch 0.41259169578552246 ---------------------------------- train loss for this epoch: 0.221377
time for this epoch 62.92936301231384 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 71 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23262754 flow loss 0.0626507 occ loss 0.16997352 time for this batch 0.38780760765075684 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19773674 flow loss 0.055439048 occ loss 0.14229491 time for this batch 0.42720580101013184 ---------------------------------- train loss for this epoch: 0.221235
time for this epoch 64.52171993255615 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 72 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25108436 flow loss 0.06422844 occ loss 0.18685251 time for this batch 0.35484886169433594 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25639877 flow loss 0.06519522 occ loss 0.19120015 time for this batch 0.451404333114624 ---------------------------------- train loss for this epoch: 0.221026
time for this epoch 66.23411297798157 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 73 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18100522 flow loss 0.0488426 occ loss 0.13216057 time for this batch 0.37381505966186523 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25943074 flow loss 0.07017973 occ loss 0.1892476 time for this batch 0.4412243366241455 ---------------------------------- train loss for this epoch: 0.222905
time for this epoch 67.97548031806946 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 74 # batch: 124 i_batch: 0.0 the loss for this batch: 0.22754382 flow loss 0.06316583 occ loss 0.16437514 time for this batch 0.3749122619628906 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20631143 flow loss 0.056534827 occ loss 0.14977404 time for this batch 0.45804500579833984 ---------------------------------- train loss for this epoch: 0.221646
time for this epoch 64.60028123855591 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 75 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24882598 flow loss 0.06757999 occ loss 0.18124266 time for this batch 0.40062975883483887 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23938765 flow loss 0.06436748 occ loss 0.17501722 time for this batch 0.41448283195495605 ---------------------------------- train loss for this epoch: 0.221442
time for this epoch 63.79179644584656 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 76 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2532499 flow loss 0.06299437 occ loss 0.19025263 time for this batch 0.3424363136291504 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25098583 flow loss 0.065301284 occ loss 0.18568149 time for this batch 0.4272444248199463 ---------------------------------- train loss for this epoch: 0.219318
time for this epoch 64.6559317111969 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 77 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2567254 flow loss 0.070549265 occ loss 0.18617266 time for this batch 0.37239742279052734 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2302971 flow loss 0.06489652 occ loss 0.16539744 time for this batch 0.41963982582092285 ---------------------------------- train loss for this epoch: 0.219298
time for this epoch 64.1589424610138 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 78 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21141283 flow loss 0.05706315 occ loss 0.1543468 time for this batch 0.36356616020202637 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20881999 flow loss 0.05838967 occ loss 0.15042749 time for this batch 0.47615480422973633 ---------------------------------- train loss for this epoch: 0.219796
time for this epoch 62.833232402801514 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 79 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24639542 flow loss 0.06243541 occ loss 0.18395688 time for this batch 0.42441821098327637 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2164835 flow loss 0.059195798 occ loss 0.15728515 time for this batch 0.42631101608276367 ---------------------------------- train loss for this epoch: 0.220574
time for this epoch 65.04839754104614 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 80 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2239836 flow loss 0.062237117 occ loss 0.1617431 time for this batch 0.36685752868652344 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.26244274 flow loss 0.07084959 occ loss 0.19159007 time for this batch 0.41624927520751953 ---------------------------------- train loss for this epoch: 0.219851
time for this epoch 70.93636417388916 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 81 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18277924 flow loss 0.050908178 occ loss 0.13186878 time for this batch 0.3647747039794922 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.14055707 flow loss 0.046028044 occ loss 0.09452732 time for this batch 0.3770768642425537 ---------------------------------- train loss for this epoch: 0.219437
time for this epoch 90.48381471633911 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 82 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24789946 flow loss 0.06252426 occ loss 0.18537217 time for this batch 0.30913329124450684 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2112771 flow loss 0.059794158 occ loss 0.1514801 time for this batch 0.5587899684906006 ---------------------------------- train loss for this epoch: 0.221147
time for this epoch 78.91724157333374 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 83 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25716075 flow loss 0.0709797 occ loss 0.18617764 time for this batch 0.41036319732666016 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2560681 flow loss 0.06510848 occ loss 0.19095698 time for this batch 0.43028807640075684 ---------------------------------- train loss for this epoch: 0.218543
time for this epoch 63.35146641731262 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 84 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17471504 flow loss 0.048832744 occ loss 0.12588045 time for this batch 0.3431830406188965 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.16349354 flow loss 0.04813181 occ loss 0.11535969 time for this batch 0.43465256690979004 ---------------------------------- train loss for this epoch: 0.217954
time for this epoch 65.75078654289246 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 85 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20854557 flow loss 0.05698055 occ loss 0.15156257 time for this batch 0.39388084411621094 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21781945 flow loss 0.0552953 occ loss 0.16252157 time for this batch 0.4207339286804199 ---------------------------------- train loss for this epoch: 0.218987
time for this epoch 65.59128332138062 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 86 # batch: 124 i_batch: 0.0 the loss for this batch: 0.26038668 flow loss 0.0699394 occ loss 0.19044374 time for this batch 0.3349316120147705 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1433255 flow loss 0.045341212 occ loss 0.097982295 time for this batch 0.40821242332458496 ---------------------------------- train loss for this epoch: 0.21755
time for this epoch 64.3962414264679 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 87 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2672627 flow loss 0.0666774 occ loss 0.20058188 time for this batch 0.3589339256286621 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1777343 flow loss 0.052631833 occ loss 0.12510005 time for this batch 0.41356992721557617 ---------------------------------- train loss for this epoch: 0.219121
time for this epoch 64.47300028800964 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 88 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24198037 flow loss 0.0635917 occ loss 0.17838544 time for this batch 0.3660879135131836 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.27403998 flow loss 0.06440083 occ loss 0.20963584 time for this batch 0.42774105072021484 ---------------------------------- train loss for this epoch: 0.217492
time for this epoch 64.44335675239563 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 89 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24994382 flow loss 0.067025095 occ loss 0.18291529 time for this batch 0.36452174186706543 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.18064341 flow loss 0.05052193 occ loss 0.13011903 time for this batch 0.3694436550140381 ---------------------------------- train loss for this epoch: 0.217619
time for this epoch 63.70642828941345 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 90 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23467888 flow loss 0.0649395 occ loss 0.16973618 time for this batch 0.37815165519714355 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.16951062 flow loss 0.052678965 occ loss 0.1168292 time for this batch 0.4568145275115967 ---------------------------------- train loss for this epoch: 0.218123
time for this epoch 63.487713098526 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 91 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24772969 flow loss 0.065608084 occ loss 0.18211852 time for this batch 0.34881162643432617 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.26216236 flow loss 0.06942329 occ loss 0.19273593 time for this batch 0.4221162796020508 ---------------------------------- train loss for this epoch: 0.217949
time for this epoch 64.52759408950806 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 92 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24498338 flow loss 0.06396174 occ loss 0.18101859 time for this batch 0.33783841133117676 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25558364 flow loss 0.06614224 occ loss 0.18943809 time for this batch 0.437638521194458 ---------------------------------- train loss for this epoch: 0.2173
time for this epoch 63.21777033805847 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 93 # batch: 124 i_batch: 0.0 the loss for this batch: 0.14882137 flow loss 0.04374006 occ loss 0.105079494 time for this batch 0.3658754825592041 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24108885 flow loss 0.06520323 occ loss 0.17588232 time for this batch 0.4011569023132324 ---------------------------------- train loss for this epoch: 0.217513
time for this epoch 64.43642544746399 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 94 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21079217 flow loss 0.057765912 occ loss 0.15302321 time for this batch 0.3817923069000244 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24285807 flow loss 0.0683254 occ loss 0.17452954 time for this batch 0.42262840270996094 ---------------------------------- train loss for this epoch: 0.216174
time for this epoch 65.88479399681091 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 95 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19536641 flow loss 0.052899893 occ loss 0.14246392 time for this batch 0.4195213317871094 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25377244 flow loss 0.06786675 occ loss 0.18590218 time for this batch 0.42064857482910156 ---------------------------------- train loss for this epoch: 0.218066
time for this epoch 64.65300798416138 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 96 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24350503 flow loss 0.06252372 occ loss 0.18097796 time for this batch 0.36910319328308105 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.18334612 flow loss 0.0508809 occ loss 0.13246252 time for this batch 0.42620253562927246 ---------------------------------- train loss for this epoch: 0.21585
time for this epoch 63.25399684906006 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 97 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2017233 flow loss 0.056182675 occ loss 0.14553767 time for this batch 0.38323211669921875 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24222258 flow loss 0.06238881 occ loss 0.1798306 time for this batch 0.4120936393737793 ---------------------------------- train loss for this epoch: 0.216366
time for this epoch 62.70336294174194 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 98 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23798636 flow loss 0.060005967 occ loss 0.1779775 time for this batch 0.3928823471069336 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.14164211 flow loss 0.04296834 occ loss 0.09867212 time for this batch 0.4261317253112793 ---------------------------------- train loss for this epoch: 0.217242
time for this epoch 62.890560150146484 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 99 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2936978 flow loss 0.072620764 occ loss 0.2210733 time for this batch 0.3618040084838867 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17777193 flow loss 0.048562717 occ loss 0.12920672 time for this batch 0.38602137565612793 ---------------------------------- train loss for this epoch: 0.21566
time for this epoch 63.830899238586426 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 100 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21381983 flow loss 0.056692373 occ loss 0.15712447 time for this batch 0.3746654987335205 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2598974 flow loss 0.064536475 occ loss 0.1953577 time for this batch 0.42615389823913574 ---------------------------------- train loss for this epoch: 0.214837
time for this epoch 64.69617700576782 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 101 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21246402 flow loss 0.058914695 occ loss 0.15354629 time for this batch 0.3353245258331299 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21496193 flow loss 0.061826043 occ loss 0.15313299 time for this batch 0.39806699752807617 ---------------------------------- train loss for this epoch: 0.216378
time for this epoch 63.09880566596985 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 102 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20209222 flow loss 0.05421726 occ loss 0.14787214 time for this batch 0.38831257820129395 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2663396 flow loss 0.07240526 occ loss 0.193931 time for this batch 0.3823130130767822 ---------------------------------- train loss for this epoch: 0.217203
time for this epoch 64.37307834625244 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 103 # batch: 124 i_batch: 0.0 the loss for this batch: 0.16091003 flow loss 0.045628417 occ loss 0.115279645 time for this batch 0.3293178081512451 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22453776 flow loss 0.058568 occ loss 0.16596718 time for this batch 0.4544811248779297 ---------------------------------- train loss for this epoch: 0.214411
time for this epoch 62.72291088104248 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 104 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20666511 flow loss 0.054446053 occ loss 0.15221624 time for this batch 0.36081933975219727 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1751381 flow loss 0.04794734 occ loss 0.12718819 time for this batch 0.39879393577575684 ---------------------------------- train loss for this epoch: 0.214115
time for this epoch 62.125935077667236 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 105 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24645226 flow loss 0.06804368 occ loss 0.1784049 time for this batch 0.3735945224761963 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.14986375 flow loss 0.046535708 occ loss 0.10332595 time for this batch 0.4029207229614258 ---------------------------------- train loss for this epoch: 0.214418
time for this epoch 63.97379231452942 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 106 # batch: 124 i_batch: 0.0 the loss for this batch: 0.1594873 flow loss 0.04598225 occ loss 0.11350329 time for this batch 0.3959996700286865 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21782713 flow loss 0.06273955 occ loss 0.15508448 time for this batch 0.33363866806030273 ---------------------------------- train loss for this epoch: 0.214009
time for this epoch 64.23186135292053 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 107 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20062116 flow loss 0.055711035 occ loss 0.14490771 time for this batch 0.37154555320739746 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1914297 flow loss 0.053312827 occ loss 0.13811436 time for this batch 0.36293649673461914 ---------------------------------- train loss for this epoch: 0.213389
time for this epoch 64.60707974433899 No_decrease: 7 ----------------an epoch starts------------------- i_epoch: 108 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24204414 flow loss 0.06600581 occ loss 0.17603518 time for this batch 0.3536372184753418 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17829725 flow loss 0.053533547 occ loss 0.1247614 time for this batch 0.42937541007995605 ---------------------------------- train loss for this epoch: 0.216524
time for this epoch 64.43332242965698 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 109 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20673995 flow loss 0.05615323 occ loss 0.15058367 time for this batch 0.3792073726654053 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.28941056 flow loss 0.07314937 occ loss 0.21625741 time for this batch 0.45015978813171387 ---------------------------------- train loss for this epoch: 0.21396
time for this epoch 66.00393056869507 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 110 # batch: 124 i_batch: 0.0 the loss for this batch: 0.27440494 flow loss 0.06811375 occ loss 0.20628758 time for this batch 0.3572421073913574 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22531033 flow loss 0.060392033 occ loss 0.16491535 time for this batch 0.4055202007293701 ---------------------------------- train loss for this epoch: 0.212603
time for this epoch 64.43120646476746 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 111 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18521972 flow loss 0.0506422 occ loss 0.13457529 time for this batch 0.37344813346862793 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20482026 flow loss 0.058616206 occ loss 0.14620143 time for this batch 0.37374091148376465 ---------------------------------- train loss for this epoch: 0.215001
time for this epoch 64.05410432815552 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 112 # batch: 124 i_batch: 0.0 the loss for this batch: 0.14251673 flow loss 0.038523242 occ loss 0.10399166 time for this batch 0.36662936210632324 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23092045 flow loss 0.059905328 occ loss 0.17101222 time for this batch 0.4206993579864502 ---------------------------------- train loss for this epoch: 0.213278
time for this epoch 63.666606426239014 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 113 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24783549 flow loss 0.06307926 occ loss 0.18475333 time for this batch 0.3476274013519287 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.15631752 flow loss 0.046571746 occ loss 0.10974369 time for this batch 0.43724775314331055 ---------------------------------- train loss for this epoch: 0.213543
time for this epoch 63.931418657302856 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 114 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24583666 flow loss 0.06464058 occ loss 0.18119268 time for this batch 0.38300490379333496 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19352452 flow loss 0.054992218 occ loss 0.1385297 time for this batch 0.4163682460784912 ---------------------------------- train loss for this epoch: 0.21362
time for this epoch 63.80172514915466 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 115 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19152059 flow loss 0.057643306 occ loss 0.13387449 time for this batch 0.3579742908477783 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.18646188 flow loss 0.05480038 occ loss 0.13165891 time for this batch 0.3592679500579834 ---------------------------------- train loss for this epoch: 0.212537
time for this epoch 63.2809419631958 No_decrease: 7 ----------------an epoch starts------------------- i_epoch: 116 # batch: 124 i_batch: 0.0 the loss for this batch: 0.26449206 flow loss 0.070893444 occ loss 0.19359502 time for this batch 0.3414909839630127 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.16508968 flow loss 0.050160483 occ loss 0.11492708 time for this batch 0.4393153190612793 ---------------------------------- train loss for this epoch: 0.21285
time for this epoch 63.84475040435791 No_decrease: 8 ----------------an epoch starts------------------- i_epoch: 117 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23729403 flow loss 0.06634476 occ loss 0.1709463 time for this batch 0.36542320251464844 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1938456 flow loss 0.052014608 occ loss 0.14182839 time for this batch 0.39249563217163086 ---------------------------------- train loss for this epoch: 0.215585
time for this epoch 64.81944870948792 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 118 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21726498 flow loss 0.055753484 occ loss 0.16150856 time for this batch 0.3986480236053467 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.16999643 flow loss 0.049389582 occ loss 0.1206046 time for this batch 0.3654143810272217 ---------------------------------- train loss for this epoch: 0.212277
time for this epoch 58.830058336257935 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 119 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17673735 flow loss 0.05495062 occ loss 0.121784426 time for this batch 0.37479734420776367 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19653517 flow loss 0.051798802 occ loss 0.14473343 time for this batch 0.3872499465942383 ---------------------------------- train loss for this epoch: 0.211559
time for this epoch 55.46442008018494 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 120 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2563559 flow loss 0.063864015 occ loss 0.19248885 time for this batch 0.3847525119781494 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19378258 flow loss 0.050619133 occ loss 0.14316079 time for this batch 0.3590986728668213 ---------------------------------- train loss for this epoch: 0.21169
time for this epoch 56.64624547958374 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 121 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23291159 flow loss 0.063200474 occ loss 0.16970733 time for this batch 0.3690633773803711 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.26988524 flow loss 0.07041722 occ loss 0.19946429 time for this batch 0.4008328914642334 ---------------------------------- train loss for this epoch: 0.21235
time for this epoch 55.56580972671509 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 122 # batch: 124 i_batch: 0.0 the loss for this batch: 0.1601842 flow loss 0.046895944 occ loss 0.113286324 time for this batch 0.3821992874145508 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22062787 flow loss 0.05868803 occ loss 0.16193676 time for this batch 0.4092991352081299 ---------------------------------- train loss for this epoch: 0.211471
time for this epoch 61.49746370315552 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 123 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20425737 flow loss 0.05698468 occ loss 0.14726973 time for this batch 0.37255334854125977 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23772638 flow loss 0.06482458 occ loss 0.17289852 time for this batch 0.41162109375 ---------------------------------- train loss for this epoch: 0.21167
time for this epoch 61.30021691322327 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 124 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23141266 flow loss 0.06302873 occ loss 0.16838086 time for this batch 0.3486642837524414 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19742598 flow loss 0.05621269 occ loss 0.14121024 time for this batch 0.30992841720581055 ---------------------------------- train loss for this epoch: 0.212272
time for this epoch 58.568278074264526 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 125 # batch: 124 i_batch: 0.0 the loss for this batch: 0.22574507 flow loss 0.05803236 occ loss 0.16770962 time for this batch 0.36562609672546387 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2433154 flow loss 0.061901964 occ loss 0.18141054 time for this batch 0.3951303958892822 ---------------------------------- train loss for this epoch: 0.211744
time for this epoch 58.874972343444824 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 126 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2087513 flow loss 0.05419426 occ loss 0.15455434 time for this batch 0.35872602462768555 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.178696 flow loss 0.051883984 occ loss 0.12680934 time for this batch 0.42586827278137207 ---------------------------------- train loss for this epoch: 0.209993
time for this epoch 58.25347280502319 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 127 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21742555 flow loss 0.056826066 occ loss 0.16059646 time for this batch 0.32117795944213867 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.27724773 flow loss 0.07294938 occ loss 0.20429467 time for this batch 0.5063233375549316 ---------------------------------- train loss for this epoch: 0.210375
time for this epoch 56.34231472015381 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 128 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2487323 flow loss 0.065648034 occ loss 0.18308082 time for this batch 0.3290388584136963 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24110787 flow loss 0.064633034 occ loss 0.17647156 time for this batch 0.38592529296875 ---------------------------------- train loss for this epoch: 0.211516
time for this epoch 56.57375717163086 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 129 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20662975 flow loss 0.0546011 occ loss 0.152026 time for this batch 0.3309895992279053 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21364722 flow loss 0.05786028 occ loss 0.15578432 time for this batch 0.3214282989501953 ---------------------------------- train loss for this epoch: 0.211107
time for this epoch 56.306612968444824 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 130 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20145021 flow loss 0.055447947 occ loss 0.14599955 time for this batch 0.3361365795135498 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22615156 flow loss 0.06159767 occ loss 0.16455059 time for this batch 0.3213961124420166 ---------------------------------- train loss for this epoch: 0.209915
time for this epoch 56.32469820976257 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 131 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23562488 flow loss 0.06327883 occ loss 0.17234272 time for this batch 0.32899975776672363 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21874739 flow loss 0.05724965 occ loss 0.16149502 time for this batch 0.3407406806945801 ---------------------------------- train loss for this epoch: 0.210434
time for this epoch 59.72876191139221 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 132 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18971676 flow loss 0.04979682 occ loss 0.13991717 time for this batch 0.322329044342041 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20975265 flow loss 0.05819595 occ loss 0.15155402 time for this batch 0.3857383728027344 ---------------------------------- train loss for this epoch: 0.211481
time for this epoch 55.785950899124146 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 133 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23508605 flow loss 0.06311491 occ loss 0.17196804 time for this batch 0.3412330150604248 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.18694127 flow loss 0.055814847 occ loss 0.13112387 time for this batch 0.4170713424682617 ---------------------------------- train loss for this epoch: 0.210119
time for this epoch 61.182568311691284 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 134 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25390643 flow loss 0.064196825 occ loss 0.18970604 time for this batch 0.3599534034729004 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21167971 flow loss 0.05742862 occ loss 0.15424807 time for this batch 0.37728333473205566 ---------------------------------- train loss for this epoch: 0.209398
time for this epoch 59.87407159805298 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 135 # batch: 124 i_batch: 0.0 the loss for this batch: 0.1283913 flow loss 0.03851745 occ loss 0.089871965 time for this batch 0.3229830265045166 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2059222 flow loss 0.054036215 occ loss 0.15188345 time for this batch 0.39731502532958984 ---------------------------------- train loss for this epoch: 0.213667
time for this epoch 58.16420269012451 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 136 # batch: 124 i_batch: 0.0 the loss for this batch: 0.26863408 flow loss 0.074399404 occ loss 0.19423105 time for this batch 0.3361687660217285 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20852926 flow loss 0.05475616 occ loss 0.1537705 time for this batch 0.4274575710296631 ---------------------------------- train loss for this epoch: 0.21022
time for this epoch 57.904603242874146 No_decrease: 7 ----------------an epoch starts------------------- i_epoch: 137 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24111238 flow loss 0.0673532 occ loss 0.17375565 time for this batch 0.3148152828216553 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2309718 flow loss 0.06056826 occ loss 0.17040049 time for this batch 0.40639472007751465 ---------------------------------- train loss for this epoch: 0.208927
time for this epoch 57.74969267845154 No_decrease: 8 ----------------an epoch starts------------------- i_epoch: 138 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18185465 flow loss 0.049618743 occ loss 0.1322336 time for this batch 0.3713679313659668 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17702945 flow loss 0.050120205 occ loss 0.12690732 time for this batch 0.41307568550109863 ---------------------------------- train loss for this epoch: 0.209942
time for this epoch 55.91401815414429 No_decrease: 9 ----------------an epoch starts------------------- i_epoch: 139 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2628631 flow loss 0.0671072 occ loss 0.19575223 time for this batch 0.32476210594177246 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.16200754 flow loss 0.05114904 occ loss 0.11085657 time for this batch 0.30687999725341797 ---------------------------------- train loss for this epoch: 0.210415
time for this epoch 53.5046808719635 No_decrease: 10 ----------------an epoch starts------------------- i_epoch: 140 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20282146 flow loss 0.055188127 occ loss 0.14763069 time for this batch 0.30498790740966797 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22499761 flow loss 0.056701876 occ loss 0.16829264 time for this batch 0.3870532512664795 ---------------------------------- train loss for this epoch: 0.208599
time for this epoch 54.768006563186646 No_decrease: 11 ----------------an epoch starts------------------- i_epoch: 141 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19892313 flow loss 0.054397345 occ loss 0.144523 time for this batch 0.3192136287689209 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20922564 flow loss 0.05571004 occ loss 0.15351295 time for this batch 0.38930654525756836 ---------------------------------- train loss for this epoch: 0.208711
time for this epoch 56.63638877868652 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 142 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23038302 flow loss 0.06111124 occ loss 0.16926871 time for this batch 0.33443760871887207 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2550668 flow loss 0.062696934 occ loss 0.19236614 time for this batch 0.38790225982666016 ---------------------------------- train loss for this epoch: 0.209323
time for this epoch 55.44406247138977 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 143 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19009264 flow loss 0.055263642 occ loss 0.13482639 time for this batch 0.3257451057434082 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23303059 flow loss 0.060912035 occ loss 0.17211527 time for this batch 0.3746650218963623 ---------------------------------- train loss for this epoch: 0.209
time for this epoch 55.78240942955017 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 144 # batch: 124 i_batch: 0.0 the loss for this batch: 0.11835137 flow loss 0.0400748 occ loss 0.07827516 time for this batch 0.3313758373260498 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.18327872 flow loss 0.047852326 occ loss 0.13542417 time for this batch 0.3848888874053955 ---------------------------------- train loss for this epoch: 0.208211
time for this epoch 56.64357781410217 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 145 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2488807 flow loss 0.062212776 occ loss 0.1866642 time for this batch 0.38059353828430176 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24782771 flow loss 0.062110957 occ loss 0.18571348 time for this batch 0.38643336296081543 ---------------------------------- train loss for this epoch: 0.208176
time for this epoch 56.599366664886475 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 146 # batch: 124 i_batch: 0.0 the loss for this batch: 0.29785857 flow loss 0.068120055 occ loss 0.22973475 time for this batch 0.34505224227905273 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22203387 flow loss 0.056877524 occ loss 0.16515368 time for this batch 0.3803422451019287 ---------------------------------- train loss for this epoch: 0.209223
time for this epoch 55.51722049713135 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 147 # batch: 124 i_batch: 0.0 the loss for this batch: 0.25428492 flow loss 0.063405894 occ loss 0.19087556 time for this batch 0.3295407295227051 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2345484 flow loss 0.065785564 occ loss 0.1687591 time for this batch 0.35782599449157715 ---------------------------------- train loss for this epoch: 0.208218
time for this epoch 54.59795594215393 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 148 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17846173 flow loss 0.047206663 occ loss 0.13125277 time for this batch 0.315962553024292 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24633193 flow loss 0.06216304 occ loss 0.18416575 time for this batch 0.3864712715148926 ---------------------------------- train loss for this epoch: 0.208218
time for this epoch 56.1541268825531 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 149 # batch: 124 i_batch: 0.0 the loss for this batch: 0.24239168 flow loss 0.06047398 occ loss 0.18191461 time for this batch 0.321929931640625 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17228535 flow loss 0.05033914 occ loss 0.121943906 time for this batch 0.32518887519836426 ---------------------------------- train loss for this epoch: 0.207781
time for this epoch 57.129225730895996 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 150 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2244454 flow loss 0.056937907 occ loss 0.16750416 time for this batch 0.31630468368530273 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.18729609 flow loss 0.049582582 occ loss 0.13771072 time for this batch 0.35686755180358887 ---------------------------------- train loss for this epoch: 0.201661
time for this epoch 55.684991121292114 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 151 # batch: 124 i_batch: 0.0 the loss for this batch: 0.1753339 flow loss 0.047320258 occ loss 0.12801105 time for this batch 0.32454872131347656 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.192692 flow loss 0.05265817 occ loss 0.14003113 time for this batch 0.2978541851043701 ---------------------------------- train loss for this epoch: 0.200903
time for this epoch 53.048187494277954 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 152 # batch: 124 i_batch: 0.0 the loss for this batch: 0.26624894 flow loss 0.065849 occ loss 0.20039609 time for this batch 0.2990133762359619 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23105258 flow loss 0.060309287 occ loss 0.17074025 time for this batch 0.39438629150390625 ---------------------------------- train loss for this epoch: 0.200432
time for this epoch 53.53631830215454 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 153 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20125723 flow loss 0.05198226 occ loss 0.14927202 time for this batch 0.323575496673584 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.24994451 flow loss 0.06597289 occ loss 0.18396851 time for this batch 0.510509729385376 ---------------------------------- train loss for this epoch: 0.200334
time for this epoch 56.9165403842926 No_decrease: 0 ----------------an epoch starts------------------- i_epoch: 154 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20785716 flow loss 0.053217836 occ loss 0.15463658 time for this batch 0.32592201232910156 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2232609 flow loss 0.06094235 occ loss 0.1623153 time for this batch 0.39625978469848633 ---------------------------------- train loss for this epoch: 0.200436
time for this epoch 56.47639560699463 No_decrease: 1 ----------------an epoch starts------------------- i_epoch: 155 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19218272 flow loss 0.048993252 occ loss 0.14318706 time for this batch 0.32420778274536133 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23999485 flow loss 0.061932057 occ loss 0.17805924 time for this batch 0.39332151412963867 ---------------------------------- train loss for this epoch: 0.200201
time for this epoch 54.155601978302 No_decrease: 2 ----------------an epoch starts------------------- i_epoch: 156 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2069004 flow loss 0.05332841 occ loss 0.15356866 time for this batch 0.3404395580291748 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.26193628 flow loss 0.062174514 occ loss 0.19975832 time for this batch 0.3901705741882324 ---------------------------------- train loss for this epoch: 0.199967
time for this epoch 55.23315477371216 No_decrease: 3 ----------------an epoch starts------------------- i_epoch: 157 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20144634 flow loss 0.05279195 occ loss 0.14865184 time for this batch 0.30121493339538574 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19671245 flow loss 0.05231777 occ loss 0.14439194 time for this batch 0.381575345993042 ---------------------------------- train loss for this epoch: 0.200062
time for this epoch 54.60373258590698 No_decrease: 4 ----------------an epoch starts------------------- i_epoch: 158 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17137113 flow loss 0.04477831 occ loss 0.12659039 time for this batch 0.3173866271972656 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21988295 flow loss 0.058177125 occ loss 0.16170266 time for this batch 0.3918344974517822 ---------------------------------- train loss for this epoch: 0.199849
time for this epoch 57.546244859695435 No_decrease: 5 ----------------an epoch starts------------------- i_epoch: 159 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19215323 flow loss 0.053069033 occ loss 0.13908127 time for this batch 0.31949782371520996 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1993109 flow loss 0.05238954 occ loss 0.14691879 time for this batch 0.3956947326660156 ---------------------------------- train loss for this epoch: 0.200333
time for this epoch 56.44371843338013 No_decrease: 6 ----------------an epoch starts------------------- i_epoch: 160 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20478562 flow loss 0.053388152 occ loss 0.15139428 time for this batch 0.3165135383605957 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17709242 flow loss 0.047770016 occ loss 0.12932031 time for this batch 0.3697688579559326 ---------------------------------- train loss for this epoch: 0.200065
time for this epoch 55.90036463737488 No_decrease: 7 ----------------an epoch starts------------------- i_epoch: 161 # batch: 124 i_batch: 0.0 the loss for this batch: 0.20139644 flow loss 0.056214385 occ loss 0.1451792 time for this batch 0.323899507522583 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1383798 flow loss 0.037277464 occ loss 0.1011002 time for this batch 0.38036179542541504 ---------------------------------- train loss for this epoch: 0.200046
time for this epoch 57.73889207839966 No_decrease: 8 ----------------an epoch starts------------------- i_epoch: 162 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19735937 flow loss 0.05547396 occ loss 0.14188233 time for this batch 0.3212001323699951 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17293061 flow loss 0.04994178 occ loss 0.12298653 time for this batch 0.39752650260925293 ---------------------------------- train loss for this epoch: 0.199723
time for this epoch 57.77620816230774 No_decrease: 9 ----------------an epoch starts------------------- i_epoch: 163 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2317263 flow loss 0.06256308 occ loss 0.16916 time for this batch 0.3033106327056885 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.28112763 flow loss 0.069777265 occ loss 0.21134649 time for this batch 0.3989837169647217 ---------------------------------- train loss for this epoch: 0.199509
time for this epoch 57.44611048698425 No_decrease: 10 ----------------an epoch starts------------------- i_epoch: 164 # batch: 124 i_batch: 0.0 the loss for this batch: 0.28318048 flow loss 0.06697693 occ loss 0.21620008 time for this batch 0.3170745372772217 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2456922 flow loss 0.06381675 occ loss 0.1818718 time for this batch 0.3914933204650879 ---------------------------------- train loss for this epoch: 0.199636
time for this epoch 57.572893142700195 No_decrease: 11 ----------------an epoch starts------------------- i_epoch: 165 # batch: 124 i_batch: 0.0 the loss for this batch: 0.16972029 flow loss 0.048434917 occ loss 0.12128296 time for this batch 0.3256263732910156 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21637535 flow loss 0.054467782 occ loss 0.16190444 time for this batch 0.3866543769836426 ---------------------------------- train loss for this epoch: 0.199571
time for this epoch 56.720921993255615 No_decrease: 12 ----------------an epoch starts------------------- i_epoch: 166 # batch: 124 i_batch: 0.0 the loss for this batch: 0.108016655 flow loss 0.033408284 occ loss 0.074606895 time for this batch 0.32808971405029297 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1947549 flow loss 0.053989824 occ loss 0.14076224 time for this batch 0.3755362033843994 ---------------------------------- train loss for this epoch: 0.199238
time for this epoch 55.81381440162659 No_decrease: 13 ----------------an epoch starts------------------- i_epoch: 167 # batch: 124 i_batch: 0.0 the loss for this batch: 0.15822677 flow loss 0.044752914 occ loss 0.11347144 time for this batch 0.3113250732421875 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1956548 flow loss 0.05289922 occ loss 0.14275245 time for this batch 0.38080644607543945 ---------------------------------- train loss for this epoch: 0.199772
time for this epoch 56.0125253200531 No_decrease: 14 ----------------an epoch starts------------------- i_epoch: 168 # batch: 124 i_batch: 0.0 the loss for this batch: 0.2194621 flow loss 0.058450915 occ loss 0.1610081 time for this batch 0.31364011764526367 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.21686721 flow loss 0.053421393 occ loss 0.16344327 time for this batch 0.3056638240814209 ---------------------------------- train loss for this epoch: 0.199704
time for this epoch 53.48667287826538 No_decrease: 15 ----------------an epoch starts------------------- i_epoch: 169 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18125194 flow loss 0.048919376 occ loss 0.13232994 time for this batch 0.3183562755584717 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.2178165 flow loss 0.05815923 occ loss 0.1596545 time for this batch 0.3759727478027344 ---------------------------------- train loss for this epoch: 0.199398
time for this epoch 55.6176118850708 No_decrease: 16 ----------------an epoch starts------------------- i_epoch: 170 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21079533 flow loss 0.054329745 occ loss 0.15646267 time for this batch 0.32271265983581543 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1437951 flow loss 0.03959429 occ loss 0.10419866 time for this batch 0.3952035903930664 ---------------------------------- train loss for this epoch: 0.199356
time for this epoch 55.795676946640015 No_decrease: 17 ----------------an epoch starts------------------- i_epoch: 171 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19128905 flow loss 0.055332437 occ loss 0.13595349 time for this batch 0.3120403289794922 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19430304 flow loss 0.053919017 occ loss 0.14038134 time for this batch 0.37479496002197266 ---------------------------------- train loss for this epoch: 0.19926
time for this epoch 58.07227826118469 No_decrease: 18 ----------------an epoch starts------------------- i_epoch: 172 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19409262 flow loss 0.051722232 occ loss 0.14236754 time for this batch 0.3156604766845703 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.19595066 flow loss 0.04708612 occ loss 0.14886169 time for this batch 0.3868851661682129 ---------------------------------- train loss for this epoch: 0.199789
time for this epoch 57.325305700302124 No_decrease: 19 ----------------an epoch starts------------------- i_epoch: 173 # batch: 124 i_batch: 0.0 the loss for this batch: 0.1838944 flow loss 0.048196007 occ loss 0.13569577 time for this batch 0.3226451873779297 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17407499 flow loss 0.047452502 occ loss 0.12662022 time for this batch 0.39611387252807617 ---------------------------------- train loss for this epoch: 0.199076
time for this epoch 57.09229564666748 No_decrease: 20 ----------------an epoch starts------------------- i_epoch: 174 # batch: 124 i_batch: 0.0 the loss for this batch: 0.22511825 flow loss 0.058299985 occ loss 0.16681513 time for this batch 0.328416109085083 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.17836024 flow loss 0.045010284 occ loss 0.13334721 time for this batch 0.29062557220458984 ---------------------------------- train loss for this epoch: 0.198957
time for this epoch 56.195101499557495 No_decrease: 21 ----------------an epoch starts------------------- i_epoch: 175 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17183615 flow loss 0.046829987 occ loss 0.12500353 time for this batch 0.3171260356903076 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.22176304 flow loss 0.060318828 occ loss 0.16144116 time for this batch 0.3800315856933594 ---------------------------------- train loss for this epoch: 0.198952
time for this epoch 55.91214919090271 No_decrease: 22 ----------------an epoch starts------------------- i_epoch: 176 # batch: 124 i_batch: 0.0 the loss for this batch: 0.18915385 flow loss 0.051168844 occ loss 0.13798212 time for this batch 0.32608938217163086 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1437366 flow loss 0.04008964 occ loss 0.10364496 time for this batch 0.33907055854797363 ---------------------------------- train loss for this epoch: 0.199191
time for this epoch 55.730061769485474 No_decrease: 23 ----------------an epoch starts------------------- i_epoch: 177 # batch: 124 i_batch: 0.0 the loss for this batch: 0.17639445 flow loss 0.049493212 occ loss 0.1268987 time for this batch 0.3156003952026367 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.27735314 flow loss 0.06758655 occ loss 0.20976263 time for this batch 0.3895556926727295 ---------------------------------- train loss for this epoch: 0.199935
time for this epoch 55.65227246284485 No_decrease: 24 ----------------an epoch starts------------------- i_epoch: 178 # batch: 124 i_batch: 0.0 the loss for this batch: 0.1476523 flow loss 0.04087297 occ loss 0.10677728 time for this batch 0.3224673271179199 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.25809944 flow loss 0.06386791 occ loss 0.19422823 time for this batch 0.3849151134490967 ---------------------------------- train loss for this epoch: 0.199131
time for this epoch 54.78545117378235 No_decrease: 25 ----------------an epoch starts------------------- i_epoch: 179 # batch: 124 i_batch: 0.0 the loss for this batch: 0.21944323 flow loss 0.05887279 occ loss 0.16056746 time for this batch 0.31783342361450195 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20652843 flow loss 0.054528486 occ loss 0.15199685 time for this batch 0.382770299911499 ---------------------------------- train loss for this epoch: 0.198878
time for this epoch 57.09069561958313 No_decrease: 26 ----------------an epoch starts------------------- i_epoch: 180 # batch: 124 i_batch: 0.0 the loss for this batch: 0.19052848 flow loss 0.05019858 occ loss 0.14032696 time for this batch 0.31153154373168945 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.20551127 flow loss 0.05635726 occ loss 0.14915074 time for this batch 0.385603666305542 ---------------------------------- train loss for this epoch: 0.198854
time for this epoch 57.08790469169617 No_decrease: 27 ----------------an epoch starts------------------- i_epoch: 181 # batch: 124 i_batch: 0.0 the loss for this batch: 0.16077527 flow loss 0.04334706 occ loss 0.1174257 time for this batch 0.3204672336578369 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.23912345 flow loss 0.060803324 occ loss 0.1783168 time for this batch 0.385648250579834 ---------------------------------- train loss for this epoch: 0.198855
time for this epoch 56.17385387420654 No_decrease: 28 ----------------an epoch starts------------------- i_epoch: 182 # batch: 124 i_batch: 0.0 the loss for this batch: 0.15562364 flow loss 0.040993232 occ loss 0.11462846 time for this batch 0.32282233238220215 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.15093958 flow loss 0.043097693 occ loss 0.10783965 time for this batch 0.3839266300201416 ---------------------------------- train loss for this epoch: 0.198908
time for this epoch 55.856362104415894 No_decrease: 29 ----------------an epoch starts------------------- i_epoch: 183 # batch: 124 i_batch: 0.0 the loss for this batch: 0.23152345 flow loss 0.0559819 occ loss 0.17553829 time for this batch 0.3250880241394043 ---------------------------------- i_batch: 64.0 the loss for this batch: 0.1986061 flow loss 0.053061433 occ loss 0.14554173 time for this batch 0.389678955078125 ---------------------------------- train loss for this epoch: 0.198721
time for this epoch 54.26301646232605 Early stop at the 184-th epoch
def apply_to_vali_test(model, vt, f_o_mean_std):
f = vt["flow"]
f_m = vt["flow_mask"].to(device)
o = vt["occupancy"]
o_m = vt["occupancy_mask"].to(device)
f_mae, f_rmse, o_mae, o_rmse = vali_test(model, f, f_m, o, o_m, f_o_mean_std, hyper["b_s_vt"])
print ("flow_mae", f_mae)
print ("flow_rmse", f_rmse)
print ("occ_mae", o_mae)
print ("occ_rmse", o_rmse)
return f_mae, f_rmse, o_mae, o_rmse
vali_f_mae, vali_f_rmse, vali_o_mae, vali_o_rmse =\
apply_to_vali_test(trained_model, vali, f_o_mean_std)
flow_mae 35.053272603131084 flow_rmse 54.09957841016035 occ_mae 0.03839110656226632 occ_rmse 0.07866730632577427
test_f_mae, test_f_rmse, test_o_mae, test_o_rmse =\
apply_to_vali_test(trained_model, test, f_o_mean_std)
flow_mae 33.34706943010906 flow_rmse 51.37163666432371 occ_mae 0.03153476901395547 occ_rmse 0.06751021108147849